RemoteFull timeAI EngineeringAgent Systems

Senior AI Engineer

Apply Now

About Metacto

At Metacto, we partner with companies across industries to transform how work gets done. We build AI agents and agentic workflows across customer operations, finance, revenue, support, and beyond.

Working at Metacto means tackling a constantly changing mix of ambitious, real-world problems. You might redesign a critical business workflow, connect fragmented systems and data, or build an agent that becomes part of a client’s daily operations. You’ll contribute across the full lifecycle, from understanding the business problem to designing, shipping, evaluating, and continuously improving the solution in production.

We move quickly, give people meaningful ownership, and measure our success by the business outcomes we create. If you want to work at the forefront of applied AI, solve challenging problems across a diverse set of clients, and help define how agentic software is built and deployed, we’d love to hear from you.

Job Overview

We’re looking for a Senior AI Engineer to own the technical system on our operational AI engagements.

You are the technical authority on an engagement, working inside the client’s environment alongside an AI Transformation Lead, from the first diagnosis conversation through the system running in production. You set the architecture, you build the hard parts yourself, and you own what happens when real operations depend on it.

Key Responsibilities

  • Agent Architecture and Orchestration: Design and implement agentic systems capable of multi-step reasoning, planning, tool use, and workflow execution against complex operational processes, with branching, retries, self-correction, human-in-the-loop checkpoints, and reusable orchestration patterns.
  • Technical Authority on the Engagement: Own models, orchestration, data flows, integrations, environments, and security boundaries, and make and explain the reliability, cost, performance, and security trade-offs to engineers and executives alike.
  • Discovery and Solution Design: Embed with operators, process owners, and executives to understand how the work runs today, where value is lost, which workflows an agent should own, and what the system has to prove before anyone trusts it with real decisions.
  • Validation Before Commitment: Test the proposed approach against the client’s real data, systems, constraints, and failure modes before the build plan is final, and review every agent charter for the gap between what it intends and what the technology will actually do.
  • Retrieval, Grounding, and Context Engineering: Build end-to-end RAG and agentic retrieval pipelines: ingestion, chunking, embeddings, vector and hybrid search, reranking, citations, access controls, freshness, persistent memory, and token-efficient context assembly.
  • Production AI Engineering: Develop the agent logic, prompts, tools, APIs, pipelines, and operational tooling behind scalable services and event-driven workflows, with attention to reliability, resilience, security, cost efficiency, and clean integration with what the client already runs.
  • Evaluation, Guardrails, and Safety: Define what good enough to ship means for each agent and build the evals that prove it, covering trajectory and task-level success, regression suites, prompt and model versioning, trace analysis, policy checks, PII handling, and hallucination mitigation.
  • Deployment and Production Operations: Release into the client’s environment with access controls, monitoring, observability, incident handling, and rollback paths, then own production reliability once real operations depend on the system.
  • Governance and Auditability: Engineer for high-stakes and regulated decisions with data boundaries, least privilege, human oversight and escalation models, and auditable rationales for what an agent decided and why.
  • Cloud Delivery and Automation: Deploy AI services using AWS, containers, infrastructure as code, CI/CD pipelines, secrets management, observability, and operational runbooks the client’s own team can run after you hand them over.
  • Technical Direction and Mentorship: Set the patterns the engineers on the engagement build against, review the critical work, pair on the hard parts, and raise the bar for how the team builds with AI development tools.
  • Reusable Patterns and Continued Value: Feed proven components, evals, and scaffolds back into Vocion so the next engagement starts further ahead, and surface the signals from inside the work that become the next workflow worth automating.

Requirements

  • 6+ years shipping software, with 2+ taking LLM or agent systems to production under real load and real data.
  • Production Python and TypeScript, and comfort working in whatever stack the client already runs.
  • Depth across retrieval, prompt and context engineering, tool use, structured outputs, and multi-step agent orchestration.
  • Architecture you set that other engineers built against, with the trade-offs you rejected still defensible today.
  • Evaluation and validation discipline applied before commitment, not assembled after a failure.
  • Experience deploying inside enterprise or client environments, with their access controls, review gates, and constraints.
  • You hold your own with executives and non-technical operators, in writing and live.
  • Daily proficiency with AI development tools. We weigh the quality of your direction, not whether you typed every line.

Preferred Qualifications

  • Forward-deployed, embedded, or consulting experience with enterprise or mid-market clients.
  • A function we sell into: customer operations, finance, revenue operations, or healthcare operations.
  • MCP, agent interop protocols, or production observability and eval tooling such as tracing and trajectory analysis.
  • Regulated or high-stakes decision systems, where auditability and human oversight were requirements, not features.
  • Engineers who got visibly better working with you.

Position Details

  • Type: Full-Time
  • Location: Remote (US) or nearshore
  • Base Salary Range (US): $140,000 - $180,000
  • Nearshore: $6,000 - $8,000 USD / month
  • Reports to the Head of Engineering

Benefits

At Metacto, we believe that great work starts with a great workplace. We offer a competitive total rewards package that supports your well-being, growth, and financial security.

Our benefits include:

  • 100% remote work with flexibility to manage your schedule
  • Unlimited paid vacation to recharge and maintain work-life balance
  • 401(k) plan with a 400% company match on the first 6% deferred
  • Comprehensive medical, dental, and vision insurance
  • Health Savings Account (HSA) and Flexible Spending Account (FSA) options
  • Group term life insurance, plus additional coverage options

How We Hire

  1. A 30-minute intro with our Head of Engineering
  2. A look at one of your public repos, discussed with you
  3. A working session on a real engagement problem, sanitized
  4. A values conversation with our CEO

No take-home that eats your weekend. If the working session runs long at the senior level, we pay for it.

Not sure which level you are? Apply to the one closest and tell us what you have shipped. We level in the process.

Join the Team

Ready to Join metacto?

Work with a team that ships real products for real companies. Bring your best—we'll do the same.

45 minutes
No prep required
Leave with one or two AI opportunities mapped

Subscribe to our newsletter

Be the first to get insights on Operational AI, engineering quality, and building systems that move real business metrics.

By subscribing you agree to ourPrivacy Policy.